Exploring the spectroscopic diversity of type Ia supernovae with Deep Learning and Unsupervised Clustering

The existence of multiple subclasses of type Ia supernovae (SNeIa) has been the subject of great debate in the last decade. In this work, we show how machine learning tools facilitate identification of subtypes of SNe Ia. Using Deep Learning for dimensionality reduction, we were capable of performin...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Astronomical Union 2016-10, Vol.12 (S325), p.247-252
Main Authors: Ishida, Emille E. O., Sasdelli, Michele, Vilalta, Ricardo, Aguena, Michel, Busti, Vinicius C., Camacho, Hugo, Trindade, Arlindo M. M., Gieseke, Fabian, de Souza, Rafael S., Fantaye, Yabebal T., Mazzali, Paolo A.
Format: Article
Language:English
Subjects:
Astronomy
Clustering
Contributed Papers
Deep learning
Machine learning
Parameter identification
Physical properties
Principal components analysis
Reduction
Supernovae
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The existence of multiple subclasses of type Ia supernovae (SNeIa) has been the subject of great debate in the last decade. In this work, we show how machine learning tools facilitate identification of subtypes of SNe Ia. Using Deep Learning for dimensionality reduction, we were capable of performing such identification in a parameter space of significantly lower dimension than its principal component analysis counterpart. This is evidence that the progenitor system and the explosion mechanism can be described with a small number of initial physical parameters. All tools used here are publicly available in the Python package DRACULA (Dimensionality Reduction And Clustering for Unsupervised Learning in Astronomy) and can be found within COINtoolbox (https://github.com/COINtoolbox/DRACULA).
ISSN:1743-9213
1743-9221
DOI:10.1017/S174392131601293X